Paper: Modeling Organization in Student Essays

ACL ID D10-1023
Title Modeling Organization in Student Essays
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2010

Automated essay scoring is one of the most important educational applications of natural language processing. Recently, researchers have begun exploring methods of scoring es- says with respect to particular dimensions of quality such as coherence, technical errors, and relevance to prompt, but there is rela- tively little work on modeling organization. We present a new annotated corpus and pro- pose heuristic-based and learning-based ap- proaches to scoring essays along the organi- zation dimension, utilizing techniques that in- volve sequence alignment, alignment kernels, and string kernels.